Hello everyone,
Does anybody know whether it's possible to calculate extract major axis
regression residuals on the results of a major axis Model II regression done by
lmodel2?
Many thanks,
Orca
Example :
> data1 data1
SSTo SSTp
1 17.21 20.36
2 19.61 20.19
3 18.60 20.08
4 18.76 19.71
5 18.24 20.48
6 19.10 20.56
7 20.45 20.56
8 18.68 19.71
9 16.55 20.48
10 17.33 20.60
11 18.12 18.93
12 18.02 18.65
13 18.43 18.90
14 18.57 18.62
15 17.40 18.79
16 18.91 19.28
17 18.43 18.58
18 17.02 18.40
19 16.96 17.79
20 17.05 17.82
21 16.98 18.07
22 16.86 18.00
23 17.00 17.79
24 16.70 18.18
25 15.93 18.07
26 17.06 17.85
> Reg1<-lmodel2(SSTo~SSTp,data=data1,"interval","interval",99)
> Reg1
Model II regression
Call: lmodel2(formula = SSTo ~ SSTp, data = data1, range.y =
"interval", range.x = "interval", nperm = 99)
n = 26 r = 0.5671202 r-square = 0.3216254
Parametric P-values: 2-tailed = 0.002517785 1-tailed = 0.001258892
Angle between the two OLS regression lines = 30.86925 degrees
Permutation tests of OLS, MA, RMA slopes: 1-tailed, tail corresponding to sign
A permutation test of r is equivalent to a permutation test of the OLS slope
P-perm for SMA = NA because the SMA slope cannot be tested
Regression results
Method Intercept Slope Angle (degrees) P-perm (1-tailed)
1 OLS 6.651441 0.5862273 30.38000 0.01
2 MA -2.397667 1.0601457 46.67227 0.01
3 SMA -1.892541 1.0336913 45.94911 NA
4 RMA 3.144884 0.7698721 37.59167 0.01
Confidence intervals
Method 2.5%-Intercept 97.5%-Intercept 2.5%-Slope 97.5%-Slope
1 OLS -0.2070452 13.509927 0.2275463 0.9449083
2 MA -22.1054387 7.308805 0.5517999 2.0922780
3 SMA -9.8957401 3.801737 0.7354715 1.4528336
4 RMA -7.3480741 11.432676 0.3358252 1.3194076
Eigenvalues: 1.751428 0.4828554
H statistic used for computing C.I. of MA: 0.09327046
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
